FASTer：通过神经动作分词实现高效的自回归视觉语言动作建模
FASTer: Toward Efficient Autoregressive Vision Language Action Modeling via Neural Action Tokenization
AI总结：
FASTer通过神经动作分词实现高效自回归视觉语言动作建模，提升机器人学习的推理效率和任务性能。
摘要：
自回归视觉语言动作（VLA）模型最近在机器人操作中展示了强大的能力。然而，其核心过程动作分词往往涉及重建保真度与推理效率之间的权衡。我们介绍了FASTer，一个统一的高效且可推广的机器人学习框架，它集成了可学习的分词器和基于其构建的自回归策略。FASTerVQ将动作块编码为单通道图像，捕捉全局时空依赖性的同时保持高压缩比。FASTerVLA在此分词器基础上构建了分块自回归解码和轻量级动作专家，实现了更快的推理和更高的任务性能。在模拟和现实世界基准上的广泛实验表明，FASTerVQ在重建质量、高令牌利用率和强跨任务和跨身体泛化方面表现优异，而FASTerVLA进一步提高了整体能力，在推理速度和任务性能上超过了之前的最先进VLA模型。
英文摘要：
Autoregressive vision-language-action (VLA) models have recently demonstrated strong capabilities in robotic manipulation. However, their core process of action tokenization often involves a trade-off between reconstruction fidelity and inference efficiency. We introduce FASTer, a unified framework for efficient and generalizable robot learning that integrates a learnable tokenizer with an autoregressive policy built upon it. FASTerVQ encodes action chunks as single-channel images, capturing global spatio-temporal dependencies while maintaining a high compression ratio. FASTerVLA builds on this tokenizer with block-wise autoregressive decoding and a lightweight action expert, achieving both faster inference and higher task performance. Extensive experiments across simulated and real-world benchmarks show that FASTerVQ delivers superior reconstruction quality, high token utilization, and strong cross-task and cross-embodiment generalization, while FASTerVLA further improves overall capability, surpassing previous state-of-the-art VLA models in both inference speed and task performance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
